TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning.
Quang Minh DinhMinh Khoi HoAnh Quan DangHung Phong TranPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- visual analysis
- speech recognition
- probabilistic model
- document retrieval
- retrieval model
- video data
- test collection
- mixture model
- language modelling
- information retrieval
- query expansion
- context sensitive
- statistical language models
- ad hoc information retrieval
- visual information
- video content
- smoothing methods
- vector space model
- video search
- multimedia
- language model for information retrieval
- pseudo relevance feedback
- relevance model
- video retrieval
- hidden markov models
- document ranking
- query terms
- retrieval systems
- visual features
- word clouds